linux_dsm_epyc7002/kernel/time/tick-broadcast.c

823 lines
21 KiB
C
Raw Normal View History

/*
* linux/kernel/time/tick-broadcast.c
*
* This file contains functions which emulate a local clock-event
* device via a broadcast event source.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
*
* This code is licenced under the GPL version 2. For details see
* kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
[S390] genirq/clockevents: move irq affinity prototypes/inlines to interrupt.h > Generic code is not supposed to include irq.h. Replace this include > by linux/hardirq.h instead and add/replace an include of linux/irq.h > in asm header files where necessary. > This change should only matter for architectures that make use of > GENERIC_CLOCKEVENTS. > Architectures in question are mips, x86, arm, sh, powerpc, uml and sparc64. > > I did some cross compile tests for mips, x86_64, arm, powerpc and sparc64. > This patch fixes also build breakages caused by the include replacement in > tick-common.h. I generally dislike adding optional linux/* includes in asm/* includes - I'm nervous about this causing include loops. However, there's a separate point to be discussed here. That is, what interfaces are expected of every architecture in the kernel. If generic code wants to be able to set the affinity of interrupts, then that needs to become part of the interfaces listed in linux/interrupt.h rather than linux/irq.h. So what I suggest is this approach instead (against Linus' tree of a couple of days ago) - we move irq_set_affinity() and irq_can_set_affinity() to linux/interrupt.h, change the linux/irq.h includes to linux/interrupt.h and include asm/irq_regs.h where needed (asm/irq_regs.h is supposed to be rarely used include since not much touches the stacked parent context registers.) Build tested on ARM PXA family kernels and ARM's Realview platform kernels which both use genirq. [ tglx@linutronix.de: add GENERIC_HARDIRQ dependencies ] Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 12:46:24 +07:00
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/module.h>
#include "tick-internal.h"
/*
* Broadcast support for broken x86 hardware, where the local apic
* timer stops in C3 state.
*/
static struct tick_device tick_broadcast_device;
static cpumask_var_t tick_broadcast_mask;
static cpumask_var_t tmpmask;
static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
#else
static inline void tick_broadcast_clear_oneshot(int cpu) { }
#endif
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
/*
* Debugging: see timer_list.c
*/
struct tick_device *tick_get_broadcast_device(void)
{
return &tick_broadcast_device;
}
struct cpumask *tick_get_broadcast_mask(void)
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
{
return tick_broadcast_mask;
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
}
/*
* Start the device in periodic mode
*/
static void tick_broadcast_start_periodic(struct clock_event_device *bc)
{
if (bc)
tick_setup_periodic(bc, 1);
}
/*
* Check, if the device can be utilized as broadcast device:
*/
static bool tick_check_broadcast_device(struct clock_event_device *curdev,
struct clock_event_device *newdev)
{
if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
(newdev->features & CLOCK_EVT_FEAT_C3STOP))
return false;
if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
!(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
return false;
return !curdev || newdev->rating > curdev->rating;
}
/*
* Conditionally install/replace broadcast device
*/
void tick_install_broadcast_device(struct clock_event_device *dev)
{
struct clock_event_device *cur = tick_broadcast_device.evtdev;
if (!tick_check_broadcast_device(cur, dev))
return;
if (!try_module_get(dev->owner))
return;
clockevents_exchange_device(cur, dev);
if (cur)
cur->event_handler = clockevents_handle_noop;
tick_broadcast_device.evtdev = dev;
if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(dev);
/*
* Inform all cpus about this. We might be in a situation
* where we did not switch to oneshot mode because the per cpu
* devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack
* of a oneshot capable broadcast device. Without that
* notification the systems stays stuck in periodic mode
* forever.
*/
if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_clock_notify();
}
/*
* Check, if the device is the broadcast device
*/
int tick_is_broadcast_device(struct clock_event_device *dev)
{
return (dev && tick_broadcast_device.evtdev == dev);
}
static void err_broadcast(const struct cpumask *mask)
{
pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
}
static void tick_device_setup_broadcast_func(struct clock_event_device *dev)
{
if (!dev->broadcast)
dev->broadcast = tick_broadcast;
if (!dev->broadcast) {
pr_warn_once("%s depends on broadcast, but no broadcast function available\n",
dev->name);
dev->broadcast = err_broadcast;
}
}
/*
* Check, if the device is disfunctional and a place holder, which
* needs to be handled by the broadcast device.
*/
int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
{
unsigned long flags;
int ret = 0;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
* Devices might be registered with both periodic and oneshot
* mode disabled. This signals, that the device needs to be
* operated from the broadcast device and is a placeholder for
* the cpu local device.
*/
if (!tick_device_is_functional(dev)) {
dev->event_handler = tick_handle_periodic;
tick_device_setup_broadcast_func(dev);
cpumask_set_cpu(cpu, tick_broadcast_mask);
tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
ret = 1;
} else {
/*
* When the new device is not affected by the stop
* feature and the cpu is marked in the broadcast mask
* then clear the broadcast bit.
*/
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
int cpu = smp_processor_id();
cpumask_clear_cpu(cpu, tick_broadcast_mask);
tick_broadcast_clear_oneshot(cpu);
} else {
tick_device_setup_broadcast_func(dev);
}
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
return ret;
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
int tick_receive_broadcast(void)
{
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
struct clock_event_device *evt = td->evtdev;
if (!evt)
return -ENODEV;
if (!evt->event_handler)
return -EINVAL;
evt->event_handler(evt);
return 0;
}
#endif
/*
* Broadcast the event to the cpus, which are set in the mask (mangled).
*/
static void tick_do_broadcast(struct cpumask *mask)
{
int cpu = smp_processor_id();
struct tick_device *td;
/*
* Check, if the current cpu is in the mask
*/
if (cpumask_test_cpu(cpu, mask)) {
cpumask_clear_cpu(cpu, mask);
td = &per_cpu(tick_cpu_device, cpu);
td->evtdev->event_handler(td->evtdev);
}
if (!cpumask_empty(mask)) {
/*
* It might be necessary to actually check whether the devices
* have different broadcast functions. For now, just use the
* one of the first device. This works as long as we have this
* misfeature only on x86 (lapic)
*/
td = &per_cpu(tick_cpu_device, cpumask_first(mask));
td->evtdev->broadcast(mask);
}
}
/*
* Periodic broadcast:
* - invoke the broadcast handlers
*/
static void tick_do_periodic_broadcast(void)
{
raw_spin_lock(&tick_broadcast_lock);
cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
tick_do_broadcast(tmpmask);
raw_spin_unlock(&tick_broadcast_lock);
}
/*
* Event handler for periodic broadcast ticks
*/
static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
ktime_t next;
tick_do_periodic_broadcast();
/*
* The device is in periodic mode. No reprogramming necessary:
*/
if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
return;
/*
* Setup the next period for devices, which do not have
* periodic mode. We read dev->next_event first and add to it
* when the event already expired. clockevents_program_event()
* sets dev->next_event only when the event is really
* programmed to the device.
*/
for (next = dev->next_event; ;) {
next = ktime_add(next, tick_period);
if (!clockevents_program_event(dev, next, false))
return;
tick_do_periodic_broadcast();
}
}
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
*/
2009-08-18 04:34:59 +07:00
static void tick_do_broadcast_on_off(unsigned long *reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
2009-08-18 04:34:59 +07:00
unsigned long flags;
int cpu, bc_stopped;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
cpu = smp_processor_id();
td = &per_cpu(tick_cpu_device, cpu);
dev = td->evtdev;
bc = tick_broadcast_device.evtdev;
/*
* Is the device not affected by the powerstate ?
*/
if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
goto out;
if (!tick_device_is_functional(dev))
goto out;
bc_stopped = cpumask_empty(tick_broadcast_mask);
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
clockevents_shutdown(dev);
}
if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
if (!tick_broadcast_force &&
cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
}
break;
}
if (cpumask_empty(tick_broadcast_mask)) {
if (!bc_stopped)
clockevents_shutdown(bc);
} else if (bc_stopped) {
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
tick_broadcast_start_periodic(bc);
else
tick_broadcast_setup_oneshot(bc);
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop.
*/
void tick_broadcast_on_off(unsigned long reason, int *oncpu)
{
if (!cpumask_test_cpu(*oncpu, cpu_online_mask))
printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
"offline CPU #%d\n", *oncpu);
else
2009-08-18 04:34:59 +07:00
tick_do_broadcast_on_off(&reason);
}
/*
* Set the periodic handler depending on broadcast on/off
*/
void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
{
if (!broadcast)
dev->event_handler = tick_handle_periodic;
else
dev->event_handler = tick_handle_periodic_broadcast;
}
/*
* Remove a CPU from broadcasting
*/
void tick_shutdown_broadcast(unsigned int *cpup)
{
struct clock_event_device *bc;
unsigned long flags;
unsigned int cpu = *cpup;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
cpumask_clear_cpu(cpu, tick_broadcast_mask);
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
if (bc && cpumask_empty(tick_broadcast_mask))
clockevents_shutdown(bc);
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
void tick_suspend_broadcast(void)
{
struct clock_event_device *bc;
unsigned long flags;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
if (bc)
clockevents_shutdown(bc);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
int tick_resume_broadcast(void)
{
struct clock_event_device *bc;
unsigned long flags;
int broadcast = 0;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
if (bc) {
clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME);
switch (tick_broadcast_device.mode) {
case TICKDEV_MODE_PERIODIC:
if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(bc);
broadcast = cpumask_test_cpu(smp_processor_id(),
tick_broadcast_mask);
break;
case TICKDEV_MODE_ONESHOT:
if (!cpumask_empty(tick_broadcast_mask))
broadcast = tick_resume_broadcast_oneshot(bc);
break;
}
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
return broadcast;
}
#ifdef CONFIG_TICK_ONESHOT
static cpumask_var_t tick_broadcast_oneshot_mask;
static cpumask_var_t tick_broadcast_pending_mask;
tick: Handle broadcast wakeup of multiple cpus Some brilliant hardware implementations wake multiple cores when the broadcast timer fires. This leads to the following interesting problem: CPU0 CPU1 wakeup from idle wakeup from idle leave broadcast mode leave broadcast mode restart per cpu timer restart per cpu timer go back to idle handle broadcast (empty mask) enter broadcast mode programm broadcast device enter broadcast mode programm broadcast device So what happens is that due to the forced reprogramming of the cpu local timer, we need to set a event in the future. Now if we manage to go back to idle before the timer fires, we switch off the timer and arm the broadcast device with an already expired time (covered by forced mode). So in the worst case we repeat the above ping pong forever. Unfortunately we have no information about what caused the wakeup, but we can check current time against the expiry time of the local cpu. If the local event is already in the past, we know that the broadcast timer is about to fire and send an IPI. So we mark ourself as an IPI target even if we left broadcast mode and avoid the reprogramming of the local cpu timer. This still leaves the possibility that a CPU which is not handling the broadcast interrupt is going to reach idle again before the IPI arrives. This can't be solved in the core code and will be handled in follow up patches. Reported-by: Jason Liu <liu.h.jason@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Veen <arjan@infradead.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Link: http://lkml.kernel.org/r/20130306111537.492045206@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-03-06 18:18:35 +07:00
static cpumask_var_t tick_broadcast_force_mask;
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
/*
* Exposed for debugging: see timer_list.c
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
*/
struct cpumask *tick_get_broadcast_oneshot_mask(void)
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
{
return tick_broadcast_oneshot_mask;
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:15 +07:00
}
/*
* Called before going idle with interrupts disabled. Checks whether a
* broadcast event from the other core is about to happen. We detected
* that in tick_broadcast_oneshot_control(). The callsite can use this
* to avoid a deep idle transition as we are about to get the
* broadcast IPI right away.
*/
int tick_check_broadcast_expired(void)
{
return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask);
}
/*
* Set broadcast interrupt affinity
*/
static void tick_broadcast_set_affinity(struct clock_event_device *bc,
const struct cpumask *cpumask)
{
if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
return;
if (cpumask_equal(bc->cpumask, cpumask))
return;
bc->cpumask = cpumask;
irq_set_affinity(bc->irq, bc->cpumask);
}
static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
ktime_t expires, int force)
{
int ret;
tick: Ensure that the broadcast device is initialized Santosh found another trap when we avoid to initialize the broadcast device in the switch_to_oneshot code. The broadcast device might be still in SHUTDOWN state when we actually need to use it. That obviously breaks, as set_next_event() is called on a shutdown device. This did not break on x86, but Suresh analyzed it: From the review, most likely on Sven's system we are force enabling the hpet using the pci quirk's method very late. And in this case, hpet_clockevent (which will be global_clock_event) handler can be null, specifically as this platform might not be using deeper c-states and using the reliable APIC timer. Prior to commit 'fa4da365bc7772c', that handler will be set to 'tick_handle_oneshot_broadcast' when we switch the broadcast timer to oneshot mode, even though we don't use it. Post commit 'fa4da365bc7772c', we stopped switching the broadcast mode to oneshot as this is not really needed and his platform's global_clock_event's handler will remain null. While on my SNB laptop, same is set to 'clockevents_handle_noop' because hpet gets enabled very early. (noop handler on my platform set when the early enabled hpet timer gets replaced by the lapic timer). But the commit 'fa4da365bc7772c' tracked the broadcast timer mode in the SW as oneshot, even though it didn't touch the HW timer. During resume however, tick_resume_broadcast() saw the SW broadcast mode as oneshot and actually programmed the broadcast device also into oneshot mode. So this triggered the null pointer de-reference after the hpet wraps around and depending on what the hpet counter is set to. On the normal platforms where hpet gets enabled early we should be seeing a spurious interrupt (in my SNB laptop I see one spurious interrupt after around 5 minutes ;) which is 32-bit hpet counter wraparound time), but that's a separate issue. Enforce the mode setting when trying to set an event. Reported-and-tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: torvalds@linux-foundation.org Cc: svenjoac@gmx.de Cc: rjw@sisk.pl Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1204181723350.2542@ionos
2012-04-18 22:31:58 +07:00
if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
ret = clockevents_program_event(bc, expires, force);
if (!ret)
tick_broadcast_set_affinity(bc, cpumask_of(cpu));
return ret;
}
int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
return 0;
}
/*
* Called from irq_enter() when idle was interrupted to reenable the
* per cpu device.
*/
void tick_check_oneshot_broadcast(int cpu)
{
if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
}
}
/*
* Handle oneshot mode broadcasting
*/
static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
{
struct tick_device *td;
ktime_t now, next_event;
int cpu, next_cpu = 0;
raw_spin_lock(&tick_broadcast_lock);
again:
dev->next_event.tv64 = KTIME_MAX;
next_event.tv64 = KTIME_MAX;
cpumask_clear(tmpmask);
now = ktime_get();
/* Find all expired events */
for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event.tv64 <= now.tv64) {
cpumask_set_cpu(cpu, tmpmask);
/*
* Mark the remote cpu in the pending mask, so
* it can avoid reprogramming the cpu local
* timer in tick_broadcast_oneshot_control().
*/
cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
} else if (td->evtdev->next_event.tv64 < next_event.tv64) {
next_event.tv64 = td->evtdev->next_event.tv64;
next_cpu = cpu;
}
}
tick: Handle broadcast wakeup of multiple cpus Some brilliant hardware implementations wake multiple cores when the broadcast timer fires. This leads to the following interesting problem: CPU0 CPU1 wakeup from idle wakeup from idle leave broadcast mode leave broadcast mode restart per cpu timer restart per cpu timer go back to idle handle broadcast (empty mask) enter broadcast mode programm broadcast device enter broadcast mode programm broadcast device So what happens is that due to the forced reprogramming of the cpu local timer, we need to set a event in the future. Now if we manage to go back to idle before the timer fires, we switch off the timer and arm the broadcast device with an already expired time (covered by forced mode). So in the worst case we repeat the above ping pong forever. Unfortunately we have no information about what caused the wakeup, but we can check current time against the expiry time of the local cpu. If the local event is already in the past, we know that the broadcast timer is about to fire and send an IPI. So we mark ourself as an IPI target even if we left broadcast mode and avoid the reprogramming of the local cpu timer. This still leaves the possibility that a CPU which is not handling the broadcast interrupt is going to reach idle again before the IPI arrives. This can't be solved in the core code and will be handled in follow up patches. Reported-by: Jason Liu <liu.h.jason@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Veen <arjan@infradead.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Link: http://lkml.kernel.org/r/20130306111537.492045206@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-03-06 18:18:35 +07:00
/* Take care of enforced broadcast requests */
cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
cpumask_clear(tick_broadcast_force_mask);
/*
* Sanity check. Catch the case where we try to broadcast to
* offline cpus.
*/
if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
cpumask_and(tmpmask, tmpmask, cpu_online_mask);
/*
* Wakeup the cpus which have an expired event.
*/
tick_do_broadcast(tmpmask);
/*
* Two reasons for reprogram:
*
* - The global event did not expire any CPU local
* events. This happens in dyntick mode, as the maximum PIT
* delta is quite small.
*
* - There are pending events on sleeping CPUs which were not
* in the event mask
*/
if (next_event.tv64 != KTIME_MAX) {
/*
* Rearm the broadcast device. If event expired,
* repeat the above
*/
if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
goto again;
}
raw_spin_unlock(&tick_broadcast_lock);
}
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
*/
void tick_broadcast_oneshot_control(unsigned long reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags;
tick: Handle broadcast wakeup of multiple cpus Some brilliant hardware implementations wake multiple cores when the broadcast timer fires. This leads to the following interesting problem: CPU0 CPU1 wakeup from idle wakeup from idle leave broadcast mode leave broadcast mode restart per cpu timer restart per cpu timer go back to idle handle broadcast (empty mask) enter broadcast mode programm broadcast device enter broadcast mode programm broadcast device So what happens is that due to the forced reprogramming of the cpu local timer, we need to set a event in the future. Now if we manage to go back to idle before the timer fires, we switch off the timer and arm the broadcast device with an already expired time (covered by forced mode). So in the worst case we repeat the above ping pong forever. Unfortunately we have no information about what caused the wakeup, but we can check current time against the expiry time of the local cpu. If the local event is already in the past, we know that the broadcast timer is about to fire and send an IPI. So we mark ourself as an IPI target even if we left broadcast mode and avoid the reprogramming of the local cpu timer. This still leaves the possibility that a CPU which is not handling the broadcast interrupt is going to reach idle again before the IPI arrives. This can't be solved in the core code and will be handled in follow up patches. Reported-by: Jason Liu <liu.h.jason@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Veen <arjan@infradead.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Link: http://lkml.kernel.org/r/20130306111537.492045206@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-03-06 18:18:35 +07:00
ktime_t now;
int cpu;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
return;
/*
* We are called with preemtion disabled from the depth of the
* idle code, so we can't be moved away.
*/
cpu = smp_processor_id();
td = &per_cpu(tick_cpu_device, cpu);
dev = td->evtdev;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
return;
bc = tick_broadcast_device.evtdev;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
tick: Handle broadcast wakeup of multiple cpus Some brilliant hardware implementations wake multiple cores when the broadcast timer fires. This leads to the following interesting problem: CPU0 CPU1 wakeup from idle wakeup from idle leave broadcast mode leave broadcast mode restart per cpu timer restart per cpu timer go back to idle handle broadcast (empty mask) enter broadcast mode programm broadcast device enter broadcast mode programm broadcast device So what happens is that due to the forced reprogramming of the cpu local timer, we need to set a event in the future. Now if we manage to go back to idle before the timer fires, we switch off the timer and arm the broadcast device with an already expired time (covered by forced mode). So in the worst case we repeat the above ping pong forever. Unfortunately we have no information about what caused the wakeup, but we can check current time against the expiry time of the local cpu. If the local event is already in the past, we know that the broadcast timer is about to fire and send an IPI. So we mark ourself as an IPI target even if we left broadcast mode and avoid the reprogramming of the local cpu timer. This still leaves the possibility that a CPU which is not handling the broadcast interrupt is going to reach idle again before the IPI arrives. This can't be solved in the core code and will be handled in follow up patches. Reported-by: Jason Liu <liu.h.jason@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Veen <arjan@infradead.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Link: http://lkml.kernel.org/r/20130306111537.492045206@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-03-06 18:18:35 +07:00
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
* if the cpu local event is earlier than the
* broadcast event. If the current CPU is in
* the force mask, then we are going to be
* woken by the IPI right away.
*/
if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
dev->next_event.tv64 < bc->next_event.tv64)
tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
if (dev->next_event.tv64 == KTIME_MAX)
goto out;
/*
* The cpu which was handling the broadcast
* timer marked this cpu in the broadcast
* pending mask and fired the broadcast
* IPI. So we are going to handle the expired
* event anyway via the broadcast IPI
* handler. No need to reprogram the timer
* with an already expired event.
*/
if (cpumask_test_and_clear_cpu(cpu,
tick_broadcast_pending_mask))
goto out;
tick: Handle broadcast wakeup of multiple cpus Some brilliant hardware implementations wake multiple cores when the broadcast timer fires. This leads to the following interesting problem: CPU0 CPU1 wakeup from idle wakeup from idle leave broadcast mode leave broadcast mode restart per cpu timer restart per cpu timer go back to idle handle broadcast (empty mask) enter broadcast mode programm broadcast device enter broadcast mode programm broadcast device So what happens is that due to the forced reprogramming of the cpu local timer, we need to set a event in the future. Now if we manage to go back to idle before the timer fires, we switch off the timer and arm the broadcast device with an already expired time (covered by forced mode). So in the worst case we repeat the above ping pong forever. Unfortunately we have no information about what caused the wakeup, but we can check current time against the expiry time of the local cpu. If the local event is already in the past, we know that the broadcast timer is about to fire and send an IPI. So we mark ourself as an IPI target even if we left broadcast mode and avoid the reprogramming of the local cpu timer. This still leaves the possibility that a CPU which is not handling the broadcast interrupt is going to reach idle again before the IPI arrives. This can't be solved in the core code and will be handled in follow up patches. Reported-by: Jason Liu <liu.h.jason@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Veen <arjan@infradead.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Link: http://lkml.kernel.org/r/20130306111537.492045206@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-03-06 18:18:35 +07:00
/*
* If the pending bit is not set, then we are
* either the CPU handling the broadcast
* interrupt or we got woken by something else.
*
* We are not longer in the broadcast mask, so
* if the cpu local expiry time is already
* reached, we would reprogram the cpu local
* timer with an already expired event.
*
* This can lead to a ping-pong when we return
* to idle and therefor rearm the broadcast
* timer before the cpu local timer was able
* to fire. This happens because the forced
* reprogramming makes sure that the event
* will happen in the future and depending on
* the min_delta setting this might be far
* enough out that the ping-pong starts.
*
* If the cpu local next_event has expired
* then we know that the broadcast timer
* next_event has expired as well and
* broadcast is about to be handled. So we
* avoid reprogramming and enforce that the
* broadcast handler, which did not run yet,
* will invoke the cpu local handler.
*
* We cannot call the handler directly from
* here, because we might be in a NOHZ phase
* and we did not go through the irq_enter()
* nohz fixups.
*/
now = ktime_get();
if (dev->next_event.tv64 <= now.tv64) {
cpumask_set_cpu(cpu, tick_broadcast_force_mask);
goto out;
}
/*
* We got woken by something else. Reprogram
* the cpu local timer device.
*/
tick_program_event(dev->next_event, 1);
}
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
* Reset the one shot broadcast for a cpu
*
* Called with tick_broadcast_lock held
*/
static void tick_broadcast_clear_oneshot(int cpu)
{
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
ktime_t expires)
{
struct tick_device *td;
int cpu;
for_each_cpu(cpu, mask) {
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev)
td->evtdev->next_event = expires;
}
}
/**
* tick_broadcast_setup_oneshot - setup the broadcast device
*/
void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
tick: Clear broadcast active bit when switching to oneshot The first cpu which switches from periodic to oneshot mode switches also the broadcast device into oneshot mode. The broadcast device serves as a backup for per cpu timers which stop in deeper C-states. To avoid starvation of the cpus which might be in idle and depend on broadcast mode it marks the other cpus as broadcast active and sets the brodcast expiry value of those cpus to the next tick. The oneshot mode broadcast bit for the other cpus is sticky and gets only cleared when those cpus exit idle. If a cpu was not idle while the bit got set in consequence the bit prevents that the broadcast device is armed on behalf of that cpu when it enters idle for the first time after it switched to oneshot mode. In most cases that goes unnoticed as one of the other cpus has usually a timer pending which keeps the broadcast device armed with a short timeout. Now if the only cpu which has a short timer active has the bit set then the broadcast device will not be armed on behalf of that cpu and will fire way after the expected timer expiry. In the case of Christians bug report it took ~145 seconds which is about half of the wrap around time of HPET (the limit for that device) due to the fact that all other cpus had no timers armed which expired before the 145 seconds timeframe. The solution is simply to clear the broadcast active bit unconditionally when a cpu switches to oneshot mode after the first cpu switched the broadcast device over. It's not idle at that point otherwise it would not be executing that code. [ I fundamentally hate that broadcast crap. Why the heck thought some folks that when going into deep idle it's a brilliant concept to switch off the last device which brings the cpu back from that state? ] Thanks to Christian for providing all the valuable debug information! Reported-and-tested-by: Christian Hoffmann <email@christianhoffmann.info> Cc: John Stultz <johnstul@us.ibm.com> Link: http://lkml.kernel.org/r/%3Calpine.LFD.2.02.1105161105170.3078%40ionos%3E Cc: stable@kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2011-05-16 16:07:48 +07:00
int cpu = smp_processor_id();
/* Set it up only once ! */
if (bc->event_handler != tick_handle_oneshot_broadcast) {
int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
bc->event_handler = tick_handle_oneshot_broadcast;
/* Take the do_timer update */
if (!tick_nohz_full_cpu(cpu))
tick_do_timer_cpu = cpu;
/*
* We must be careful here. There might be other CPUs
* waiting for periodic broadcast. We need to set the
* oneshot_mask bits for those and program the
* broadcast device to fire.
*/
cpumask_copy(tmpmask, tick_broadcast_mask);
cpumask_clear_cpu(cpu, tmpmask);
cpumask_or(tick_broadcast_oneshot_mask,
tick_broadcast_oneshot_mask, tmpmask);
if (was_periodic && !cpumask_empty(tmpmask)) {
2012-04-18 17:08:23 +07:00
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
tick_broadcast_init_next_event(tmpmask,
tick_next_period);
tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
} else
bc->next_event.tv64 = KTIME_MAX;
tick: Clear broadcast active bit when switching to oneshot The first cpu which switches from periodic to oneshot mode switches also the broadcast device into oneshot mode. The broadcast device serves as a backup for per cpu timers which stop in deeper C-states. To avoid starvation of the cpus which might be in idle and depend on broadcast mode it marks the other cpus as broadcast active and sets the brodcast expiry value of those cpus to the next tick. The oneshot mode broadcast bit for the other cpus is sticky and gets only cleared when those cpus exit idle. If a cpu was not idle while the bit got set in consequence the bit prevents that the broadcast device is armed on behalf of that cpu when it enters idle for the first time after it switched to oneshot mode. In most cases that goes unnoticed as one of the other cpus has usually a timer pending which keeps the broadcast device armed with a short timeout. Now if the only cpu which has a short timer active has the bit set then the broadcast device will not be armed on behalf of that cpu and will fire way after the expected timer expiry. In the case of Christians bug report it took ~145 seconds which is about half of the wrap around time of HPET (the limit for that device) due to the fact that all other cpus had no timers armed which expired before the 145 seconds timeframe. The solution is simply to clear the broadcast active bit unconditionally when a cpu switches to oneshot mode after the first cpu switched the broadcast device over. It's not idle at that point otherwise it would not be executing that code. [ I fundamentally hate that broadcast crap. Why the heck thought some folks that when going into deep idle it's a brilliant concept to switch off the last device which brings the cpu back from that state? ] Thanks to Christian for providing all the valuable debug information! Reported-and-tested-by: Christian Hoffmann <email@christianhoffmann.info> Cc: John Stultz <johnstul@us.ibm.com> Link: http://lkml.kernel.org/r/%3Calpine.LFD.2.02.1105161105170.3078%40ionos%3E Cc: stable@kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2011-05-16 16:07:48 +07:00
} else {
/*
* The first cpu which switches to oneshot mode sets
* the bit for all other cpus which are in the general
* (periodic) broadcast mask. So the bit is set and
* would prevent the first broadcast enter after this
* to program the bc device.
*/
tick_broadcast_clear_oneshot(cpu);
}
}
/*
* Select oneshot operating mode for the broadcast device
*/
void tick_broadcast_switch_to_oneshot(void)
{
struct clock_event_device *bc;
unsigned long flags;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
bc = tick_broadcast_device.evtdev;
if (bc)
tick_broadcast_setup_oneshot(bc);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
* Remove a dead CPU from broadcasting
*/
void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
{
unsigned long flags;
unsigned int cpu = *cpup;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
* Clear the broadcast masks for the dead cpu, but do not stop
* the broadcast device!
*/
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
* Check, whether the broadcast device is in one shot mode
*/
int tick_broadcast_oneshot_active(void)
{
return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
}
/*
* Check whether the broadcast device supports oneshot.
*/
bool tick_broadcast_oneshot_available(void)
{
struct clock_event_device *bc = tick_broadcast_device.evtdev;
return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
}
#endif
void __init tick_broadcast_init(void)
{
zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
#ifdef CONFIG_TICK_ONESHOT
zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
#endif
}